Unit selection in a concatenative speech synthesis system using alarge speech (1996)

by A J Black Hunt, A W
Venue:Acoustics, Speech, and Signal Processing,
Add To MetaCart
Results 1 - 10 of 425

Statistical parametric speech synthesis

by Alan W Black, Heiga Zen, Keiichi Tokuda - in Proc. ICASSP, 2007 , 2007
"... This paper gives a general overview of techniques in statistical parametric speech synthesis. One of the instances of these techniques, called HMM-based generation synthesis (or simply HMM-based synthesis), has recently been shown to be very effective in generating acceptable speech synthesis. This ..."
Abstract - Cited by 179 (18 self) - Add to MetaCart
This paper gives a general overview of techniques in statistical parametric speech synthesis. One of the instances of these techniques, called HMM-based generation synthesis (or simply HMM-based synthesis), has recently been shown to be very effective in generating acceptable speech synthesis. This paper also contrasts these techniques with the more conventional unit selection technology that has dominated speech synthesis over the last ten years. Advantages and disadvantages of statistical parametric synthesis are highlighted as well as identifying where we expect the key developments to appear in the immediate future. Index Terms — Speech synthesis, hidden Markov models 1. BACKGROUND With the increase in power and resources of computer technology, building natural sounding synthetic voices has progressed from a
(Show Context)

Automatically Clustering Similar Units For Unit Selection In Speech Synthesis.

by Alan W Black, Paul Taylor - in Eurospeech97 , 1997
"... This paper describes a new method for synthesizing speech by concatenating sub-word units from a database of labelled speech. A large unit inventory is created by automatically clustering units of the same phone class based on their phonetic and prosodic context. The appropriate cluster is then sele ..."
Abstract - Cited by 138 (21 self) - Add to MetaCart
This paper describes a new method for synthesizing speech by concatenating sub-word units from a database of labelled speech. A large unit inventory is created by automatically clustering units of the same phone class based on their phonetic and prosodic context. The appropriate cluster is then selected for a target unit offering a small set of candidate units. An optimal path is found through the candidate units based on their distance from the cluster center and an acoustically based join cost. Details of the method and justification are presented. The results of experiments using two different databases are given, optimising various parameters within the system. Also a comparison with other existing selection based synthesis techniques is given showing the advantages this method has over existing ones. The method is implemented within a full text-to-speech system offering efficient natural sounding speech synthesis. 1. BACKGROUND Speech synthesis by concatenation of sub-word units ...
(Show Context)

A speech parameter generation algorithm considering global variance for HMM-based speech synthesis

by Tomoki Toda, Keiichi Tokuda - IEICE - Trans. Inf. Syst , 2007
"... This paper describes a novel parameter generation algorithm for the HMM-based speech synthesis. The conventional algorithm generates a trajectory of static features that maximizes an output probability of a parameter sequence consisting of the static and dynamic features from HMMs under an actual co ..."
Abstract - Cited by 133 (24 self) - Add to MetaCart
This paper describes a novel parameter generation algorithm for the HMM-based speech synthesis. The conventional algorithm generates a trajectory of static features that maximizes an output probability of a parameter sequence consisting of the static and dynamic features from HMMs under an actual constraint between the two features. The generated trajectory is often excessively smoothed due to the statistical processing. Using the over-smoothed trajectory causes the muffled sound. In order to alleviate the over-smoothing effect, we propose the generation algorithm considering not only the output probability used for the conventional method but also that of a global variance (GV) of the generated trajectory. The latter probability works as a penalty for a reduction of the variance of the generated trajectory. A result of a perceptual evaluation demonstrates that the proposed method causes large improvements of the naturalness of synthetic speech. 1.
(Show Context)

Applying the harmonic plus noise model in concatenative speech synthesis

by Yannis Stylianou - IEEE Trans. Speech and Audio Processing , 2001
"... Abstract—This paper describes the application of the harmonic plus noise model (HNM) for concatenative text-to-speech (TTS) synthesis. In the context of HNM, speech signals are represented as a time-varying harmonic component plus a modulated noise component. The decomposition of a speech signal int ..."
Abstract - Cited by 94 (3 self) - Add to MetaCart
Abstract—This paper describes the application of the harmonic plus noise model (HNM) for concatenative text-to-speech (TTS) synthesis. In the context of HNM, speech signals are represented as a time-varying harmonic component plus a modulated noise component. The decomposition of a speech signal into these two components allows for more natural-sounding modifications of the signal (e.g., by using different and better adapted schemes to modify each component). The parametric representation of speech using HNM provides a straightforward way of smoothing discontinuities of acoustic units around concatenation points. Formal listening tests have shown that HNM provides high-quality speech synthesis while outperforming other models for synthesis (e.g., TD-PSOLA) in intelligibility, naturalness, and pleasantness. Index Terms—Concatenative speech synthesis, fast amplitude, harmonic plus noise models, phase estimation, pitch estimation. I.
(Show Context)

Analysis of speaker adaptation algorithms for HMM-based speech synthesis and a constrained SMAPLR adaptation algorithm

by Junichi Yamagishi, Takao Kobayashi, Senior Member, Yuji Nakano, Katsumi Ogata, Juri Isogai - IEEE Trans. Audio Speech Lang. Process , 2009
"... Abstract—In this paper, we analyze the effects of several factors and configuration choices encountered during training and model construction when we want to obtain better and more stable adaptation in HMM-based speech synthesis. We then propose a new adaptation algorithm called constrained structu ..."
Abstract - Cited by 90 (28 self) - Add to MetaCart
Abstract—In this paper, we analyze the effects of several factors and configuration choices encountered during training and model construction when we want to obtain better and more stable adaptation in HMM-based speech synthesis. We then propose a new adaptation algorithm called constrained structural maximum a posteriori linear regression (CSMAPLR) whose derivation is based on the knowledge obtained in this analysis and on the results of comparing several conventional adaptation algorithms. Here, we investigate six major aspects of the speaker adaptation: initial models; the amount of the training data for the initial models; the transform functions, estimation criteria, and sensitivity of several linear regression adaptation algorithms; and combination algorithms. Analyzing the effect of the initial model, we compare speaker-dependent models, gender-independent models, and the simultaneous use of the gender-dependent models to single use of the gender-dependent models. Analyzing the effect of the transform functions, we compare the transform function for only mean vectors with that for mean vectors and covariance matrices. Analyzing the effect of the estimation criteria, we compare the ML criterion with a robust estimation criterion called structural MAP. We evaluate the sensitivity of several thresholds for the piecewise linear regression algorithms and take up methods com-bining MAP adaptation with the linear regression algorithms. We incorporate these adaptation algorithms into our speech synthesis system and present several subjective and objective evaluation results showing the utility and effectiveness of these algorithms in speaker adaptation for HMM-based speech synthesis. Index Terms—Average voice, hidden Markov model (HMM)-based speech synthesis, speaker adaptation, speech synthesis, voice conversion. I.

A System For Data-Driven Concatenative Sound Synthesis

by Diemo Schwarz, Ircam Centre Pompidou , 2000
"... In speech synthesis, concatenative data-driven synthesis methods prevail. They use a database of recorded speech and a unit selection algorithm that selects the segments that match best the utterance to be synthesized. Transferring these ideas to musical sound synthesis allows a new method of high q ..."
Abstract - Cited by 78 (10 self) - Add to MetaCart
In speech synthesis, concatenative data-driven synthesis methods prevail. They use a database of recorded speech and a unit selection algorithm that selects the segments that match best the utterance to be synthesized. Transferring these ideas to musical sound synthesis allows a new method of high quality sound synthesis. Usual synthesis methods are based on a model of the sound signal. It is very difficult to build a model that would preserve the entire fine details of sound. Concatenative synthesis achieves this by using actual recordings. This data-driven approach (as opposed to a rule-based approach) takes advantage of the information contained in the many sound recordings. For example, very naturally sounding transitions can be synthesized, since unit selection is aware of the context of the database units. The CATERPILLAR software system has been developed to allow data-driven concatenative unit selection sound synthesis. It allows high-quality instrument synthesis with high level control, explorative free synthesis from arbitrary sound databases, or resynthesis of a recording with sounds from the database. It is based on the new software-engineering concept of component-oriented software, increasing flexibility and facilitating reuse.
(Show Context)

Statistical Mapping between Articulatory Movements and Acoustic Spectrum Using a Gaussian Mixture Model

by Tomoki Toda , et al. , 2007
"... In this paper, we describe a statistical approach to both an articulatory-to-acoustic mapping and an acoustic-to-articulatory inversion mapping without using phonetic information. The joint probability density of an articulatory parameter and an acoustic parameter is modeled using a Gaussian mixture ..."
Abstract - Cited by 62 (5 self) - Add to MetaCart
In this paper, we describe a statistical approach to both an articulatory-to-acoustic mapping and an acoustic-to-articulatory inversion mapping without using phonetic information. The joint probability density of an articulatory parameter and an acoustic parameter is modeled using a Gaussian mixture model (GMM) based on a parallel acoustic-articulatory speech database. We apply the GMM-based mapping using the minimum mean-square error (MMSE) criterion, which has been proposed for voice conversion, to the two mappings. Moreover, to improve the mapping performance, we apply maximum likelihood estimation (MLE) to the GMM-based mapping method. The determination of a target parameter trajectory having appropriate static and dynamic properties is obtained by imposing an explicit relationship between static and dynamic features in the MLE-based mapping. Experimental results demonstrate that the MLE-based mapping with dynamic features can significantly improve the mapping performance compared with the MMSE-based mapping in both the articulatory-to-acoustic mapping and the inversion mapping.

Robust speaker-adaptive HMM-based text-to-speech synthesis

by Junichi Yamagishi, Takashi Nose, Heiga Zen, Zhen-hua Ling, Tomoki Toda, Keiichi Tokuda, Simon King, Steve Renals - IEEE TRANS. ON AUDIO, SPEECH AND LANGUAGE PROCESSING , 2009
"... This paper describes a speaker-adaptive HMM-based speech synthesis system. The new system, called “HTS-2007,” employs speaker adaptation (CSMAPLR+MAP), feature-space adaptive training, mixed-gender modeling, and full-covariance modeling using CSMAPLR transforms, in addition to several other techniq ..."
Abstract - Cited by 60 (18 self) - Add to MetaCart
This paper describes a speaker-adaptive HMM-based speech synthesis system. The new system, called “HTS-2007,” employs speaker adaptation (CSMAPLR+MAP), feature-space adaptive training, mixed-gender modeling, and full-covariance modeling using CSMAPLR transforms, in addition to several other techniques that have proved effective in our previous systems. Subjective evaluation results show that the new system generates significantly better quality synthetic speech than speaker-dependent approaches with realistic amounts of speech data, and that it bears comparison with speaker-dependent approaches even when large amounts of speech data are available. In addition, a comparison study with several speech synthesis techniques shows the new system is very robust: It is able to build voices from less-than-ideal speech data and synthesize good-quality speech even for out-of-domain sentences.
(Show Context)

Speaking with Hands: Creating Animated Conversational Characters from Recordings of Human Performance

by Matthew Stone, Doug DeCarlo, Insuk Oh, Christian Rodriguez, Adrian Stere, Alyssa Lees, Chris Bregler , 2004
"... We describe a method for using a database of recorded speech and captured motion to create an animated conversational character. People's utterances are composed of short, clearly-delimited phrases; in each phrase, gesture and speech go together meaningfully and synchronize at a common point of ..."
Abstract - Cited by 53 (2 self) - Add to MetaCart
We describe a method for using a database of recorded speech and captured motion to create an animated conversational character. People's utterances are composed of short, clearly-delimited phrases; in each phrase, gesture and speech go together meaningfully and synchronize at a common point of maximum emphasis. We develop tools for collecting and managing performance data that exploit this structure. The tools help create scripts for performers, help annotate and segment performance data, and structure specific messages for characters to use within application contexts. Our animations then reproduce this structure. They recombine motion samples with new speech samples to recreate coherent phrases, and blend segments of speech and motion together phraseby -phrase into extended utterances. By framing problems for utterance generation and synthesis so that they can draw closely on a talented performance, our techniques support the rapid construction of animated characters with rich and appropriate expression.

Natural-Sounding Speech Synthesis Using Variable-Length Units

by Jon R. W. Yi, James R. Glass , 1998
"... The goal of this work was to develop a speech synthesis system which concatenates variable-length units to create naturalsounding speech. Our initial work in this area showed that by careful design of system responses to ensure consistent intonation contours, natural-sounding speech synthesis was ac ..."
Abstract - Cited by 49 (4 self) - Add to MetaCart
The goal of this work was to develop a speech synthesis system which concatenates variable-length units to create naturalsounding speech. Our initial work in this area showed that by careful design of system responses to ensure consistent intonation contours, natural-sounding speech synthesis was achievable with word- and phrase-level concatenation. In order to extend the flexibility of this framework, we focused on the problem of generating novel words from a corpus of sub-word units. The design of the sub-word units was motivated by perceptual studies that investigated where speech could be spliced with minimal audible distortion and what contextual constraints were necessary to maintain in order to produce natural sounding speech. The sub-word corpus is searched during synthesis using a Viterbi search which selects a sequence of units based on how well they individually match the input specification and on how well they sound as an ensemble. This concatenative speech synthesis system, ENVOICE, has been used in a conversational information retrieval system in two application domains to convert meaning representations into speech waveforms.